Update app.py

app.py

@@ -14,8 +14,8 @@ import torch
 # Initialize model and tokenizer globally
 @st.cache_resource
 def load_model_and_tokenizer():
-    tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")
-    model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")
+    tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
+    model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
     if torch.cuda.is_available():
         model = model.to("cuda")
     return model, tokenizer